Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Grandmaster level in StarCraft II using multi-agent reinforcement learning

deepmind.com

Post reply on HN
Print view View original

71–80 of 321 posts

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#71

Post by jamra »

username90 wrote: post #31
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

They are testing the AI's ability to do tactics and strategy, not motor and visual tasks. It has built in delay and needs to move around the map to gather information just like a human, so it doesn't have any significant unfair advantages. Edit: Note that the version they sent out to the ladder had significant larger delay, significant lower APM, and didn't get any information not visible on the screen unlike the fir…

However the computer can macro while in a fight which is something people can’t dI. We would miss the fight and lose the game. It’s not just a tactics game. Attention span and where your eyes are matter.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#72

Post by bsdetector »

username90 wrote: post #31
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

They are testing the AI's ability to do tactics and strategy, not motor and visual tasks. It has built in delay and needs to move around the map to gather information just like a human, so it doesn't have any significant unfair advantages. Edit: Note that the version they sent out to the ladder had significant larger delay, significant lower APM, and didn't get any information not visible on the screen unlike the fir…

When Watson won Jeopardy, its lead designer thought a 5 ms reaction time was fair because one time a human anticipating the buzzer light got 2 ms.

Of course to any reasonable person a consistent 5 ms is obviously vastly superior to once in a blue moon lottery-winning luck.

Sounds like it's the same deal here, where the designers made some effort to level the interface playing field, but also left in some advantages like instantly being able to select individual units (or whatever it was the other players felt was not humanly possible to do). Probably because, at some level, they really want their system to win.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#73

Post by Symmetry »

Aperocky wrote: post #25
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

Or connect the computer to human neurons directly.

You'd be able to save the time it takes a nerve impulse from head to hand that way. It's not much but apparently it can be significant enough that in some DotA games shorter players are disproportionately successful in the roles requiring the fastest reflexes.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#74

Post by roenxi »

hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

Interestingly, the hardest part of AlphaStar looked like it was researching how to stop the computer winning through an overwhelming mechanical advantage.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#75

Post by the_af »

bsaul wrote: post #58

Has anyone read the actual paper ? This summary really makes it look like "mission accomplished", but this was much much more interesting than that. We saw AI do "obviously stupid things", and we also saw them improve a lot in the middle of the trial, as many youtubers showed. AI was also much more interesting when playing the protoss race, and really felt like it was responding to the opponents actions, and the othe…

> Actually not a single game made pro player realize something new about the game. Which is really embarassing, because it suggests that the AI just was able to correctly reproduce existing strategies and build orders, that it probably "learned" from existing pro games in the training sample.

Why is it embarrassing if the AI behaved like a collection of all the knowledge of existing pro players?

Obviously it'd be more interesting if we also learned something new about the game. Or AI, or both.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#76

Post by IpV8 »

neogodless wrote: post #48
v4dok wrote: post #33

Earlier quoted context omitted.

Nobody selects larvas directly? I guess I am a computer then. Way worse than Alphastar tho.

Ha! So I always did that in Brood Wars, but in SC2, I put each hatchery on a hotkey (0, 9, 8, etc.) and then just pick the units I want to queue up. No need to select individual larva any more.

I like to map tilda, tab, and caps lock to 0, 9, and 8 so that my left hand doesn't have to reach as far.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#77

Post by hamilyon2 »

hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

22 actions each 5 seconds isn't that generous. Pro players have to manage apm too. Conserve it or spend where needed. I would say it is fair.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#78

Post by bakuninsbart »

ropman76 wrote: post #27
hoseja wrote: post #15

There has always been the issue of interface when playing videogames AI vs human. Either give the human a brain-computer interface or give the AI a mouse, keyboard, monitor, robot hands and a camera. Anything else seems inherently unfair.

Or even a turn based game, where click speed does not matter...

If Google could tackle Civilizations god-aweful AI next, I'd be over the moon.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#79

Post by king-rat »

jplayer01 wrote: post #69
king-rat wrote: post #18

Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game. That also indicates an interesting flaw in how this model is trained - in the millions of games it plays against itself, how do you ensure that it tries every viable (and some inviable) strategies? Sure, it couldn't best Serral but I wonder how it would fare against Has, a player known for some pretty off the w…

> Not being robust to strategies it hasn't seen before is a serious shortcoming in a real time strategy game. I'm not sure if you've actually played or followed competitive SC2. This is absolutely normal . Players will pull something completely unexpected out of a hat and win. The losing player will learn from it in future games. That's just how it goes. Unexpected strategies are really hard to counter when you've ne…

I do actually follow competitive SC2. My point is that for DeepMind to master this game in the same way it has with Go and chess, it must be able to anticipate counter plays ad infinitum. Otherwise humans will continue to beat it.

Re: Grandmaster level in StarCraft II using multi-agent reinforcement learning

#80

Post by MiracleUser »

floitsch wrote: post #49
mieseratte wrote: post #30

Earlier quoted context omitted.

> For humans that would be almost impossible, because the screen would scroll when the mouse approaches the border. That humans cannot reliably perform these actions because of the limitations of our corporeal form means that Alphastar has an advantage over a human player. Limiting APM isn't enough.

The question isn't whether the AI still has advantages, but whether it's an unfair one. The current restrictions were implemented with input from TLO, and seem to work quite nicely. One could, of course, add more restrictions (like not noticing things on the minimap all the time...), but that's not what's it about anymore. At this point, micro is comparable to humans, and we can start to compare macro and strategy. F…

> a well executed strategy with few errors often wins, even if it wasn't optimal

I think this is hits the chord with why a lot of people are talking about this bot as cheating more than they are being outplayed.

It's like fighting an aimbot in an FPS. They arent outsmarting you, but the mechanical consistency is inhuman and you are unable to force mistakes. At best itll feel like playing someone on their best day.

The heart of gaming, and why starcrat2 in particular is popular, is finding ways to play around each others mistakes.

Honestly, they should reduce Micro to the point that humans can bully it a little bit. How does the AI handle finding new ways to trade units to its advantage against a mechanically stronger opponent? How does it try to bait the human into having to take fights with unfavorable units / strategy.. as opposed to beating through them with mechanic mastery

Post reply on HN